What is the normal distribution used for?

The normal distribution models continuous variables that result from many small independent factors: heights, weights, test scores, measurement errors, blood pressure, and financial returns. It's fundamental in statistics for hypothesis testing, confidence intervals, and regression analysis.

How do you calculate normal distribution probability?

Normal probabilities require the CDF which uses the error function: Φ(x) = (1 + erf((x-μ)/(σ√2)))/2. First standardize to Z = (x-μ)/σ, then look up Φ(Z) in standard normal tables or use the calculator. For ranges P(a ≤ X ≤ b) = Φ(b) - Φ(a).

A Z-score measures how many standard deviations a value is from the mean: Z = (X - μ)/σ. Z = 0 means exactly at the mean, Z = 1 means one standard deviation above, Z = -2 means two standard deviations below. Z-scores standardize normal distributions for comparison.

What is the 68-95-99.7 empirical rule?

The empirical rule states approximately 68% of values fall within μ ± σ, 95% within μ ± 2σ, and 99.7% within μ ± 3σ. This provides quick probability estimates without calculations and explains why values beyond ±3σ are considered unusual or outliers.

Why is the normal distribution so important?

The normal distribution is fundamental because: (1) many natural phenomena follow it, (2) the Central Limit Theorem makes sums/averages of any variables approximately normal, (3) it's mathematically tractable for analysis, and (4) it's the basis for most statistical inference procedures.

Normal Distribution Explorer

Modify Parameters and See Results

Bell curve - the most important continuous distribution

Parameters

Mean (μ): 0.0

Standard Deviation (σ): 1.0

Mean (μ)

0.00

Center of the distribution (also median and mode)

Standard Deviation (σ)

1.00

Measure of spread around the mean

Variance (σ²)

1.00

Square of the standard deviation

Statistics

Expected Value

0.0000

Variance

1.0000

Std Deviation

1.0000

Mode

0.0000

Probability Calculator

Enter lower bound a:

Enter upper bound b:

Key Properties

Real-World Applications

Heights and weights of populations
Measurement errors in scientific experiments
Test scores and IQ measurements
Blood pressure in healthy adults
Manufacturing tolerances and product dimensions
Returns on financial investments (short-term)

Adjusting Mean and Standard Deviation

Reading the PDF Curve

Understanding the CDF Display

The Explorer at Its Opening Parameters

Using the Probability Calculators

Working with Z-Scores

The Empirical Rule (68-95-99.7)

What is the Normal Distribution?

Central Limit Theorem Connection

Distribution Properties and Statistics

Related Distributions and Calculators

Adjusting Mean and Standard Deviation

Use the μ (mu) slider to shift the distribution's center along the x-axis. Values range from -10 to 10, moving the bell curve left or right without changing its shape.

Adjust σ (sigma) slider to control spread. Smaller σ creates a tall, narrow curve with values concentrated near μ. Larger σ produces a short, wide curve with more variability.

Watch how changing these parameters affects the visualization. The curve always remains symmetric around μ, with the same bell shape regardless of parameters - only location and scale change.

Reading the PDF Curve

The PDF (Probability Density Function) displays the characteristic bell-shaped curve. The peak occurs at x = μ, representing the distribution's mean, median, and mode - all equal due to symmetry.

The curve extends from -∞ to +∞ theoretically, but the calculator shows the practical range μ ± 4σ where 99.99% of probability mass resides. Areas under the curve represent probabilities.

Inflection points (where curvature changes) occur at μ ± σ. Between these points, the curve is steepest, containing about 68% of the total probability. This geometric feature helps visualize the 68-95-99.7 rule.

Understanding the CDF Display

The CDF (Cumulative Distribution Function) shows the characteristic S-curve rising from 0 to 1. At any point x, the height gives P(X ≤ x), the probability of values at or below x.

The CDF's steepest region occurs around μ where the PDF peaks. At μ itself, CDF equals 0.5 - exactly half the probability lies below the mean due to symmetry.

The CDF approaches but never quite reaches 0 or 1 at the display's edges. At μ ± 3σ, CDF values are approximately 0.0013 and 0.9987, leaving only 0.27% probability in the extreme tails combined.

The Explorer at Its Opening Parameters

The standard normal,

\mu = 0

and

\sigma = 1

, is drawn over the window

\mu \pm 4\sigma

. The density peaks at

f(0) = \frac{1}{\sqrt{2\pi}} = 0.3989

, with the red mean line through the centre of the bell.

The CDF tab shows the sigmoid crossing

0.5

exactly at the mean, and reaching

0.99997

at the right edge.

Normal, mu = 0, sigma = 1: PDF above, CDF below

The bell peaks at 1/sqrt(2 pi) = 0.3989 and the sigmoid below crosses 0.5 at the mean. Shrink sigma and the peak rises without limit: a density may exceed 1, a probability may not.

The peak height is the clearest illustration that a density is not a probability. Here it is

0.399

; shrink

\sigma

and it rises without limit, because the area underneath must stay at

1

. A density above

1

is perfectly legal, a probability above

1

is not.

The two tabs locate

\sigma

differently, which is why both are worth looking at. On the PDF it is the distance from the peak to the inflection points; on the CDF it is where the curve stops steepening. Same number, two different visual cues.

Because the Gaussian has no elementary antiderivative, the CDF cannot be written in closed form with ordinary functions — the tool evaluates it through an error-function approximation, which is why every normal probability you have ever looked up came from a table or a numerical routine rather than a formula.

Using the Probability Calculators

Enter value x in the P(X ≤ x) calculator to find the area under the curve to the left of x. This uses the error function erf(z) where z = (x - μ)/σ is the standardized Z-score.

P(X ≥ x) gives the right-tail probability, computed as 1 - P(X ≤ x). This answers questions like "What fraction of values exceed x?"

For range probabilities P(a ≤ X ≤ b), the calculator computes CDF(b) - CDF(a), giving the area under the curve between a and b. This is the fundamental probability for any continuous interval.

Working with Z-Scores

Every normal distribution calculation uses standardization: Z = (X - μ)/σ transforms values to standard normal (μ = 0, σ = 1). The calculator performs this conversion automatically.

Z-scores measure distance from the mean in standard deviation units. Z = 2 means "2 standard deviations above the mean." Z = -1.5 means "1.5 standard deviations below."

The standard normal table (Z-table) provides CDF values for Z-scores. For any normal distribution, standardize first, then look up the Z-score. This is why one table suffices for all normal distributions.

The Empirical Rule (68-95-99.7)

The 68% rule: About 68% of values fall within μ ± σ. For μ = 100, σ = 15, expect 68% of values in [85, 115].

The 95% rule: About 95% fall within μ ± 2σ. Using the same parameters, 95% lie in [70, 130]. Only 5% of values fall more than 2 standard deviations from the mean.

The 99.7% rule: About 99.7% fall within μ ± 3σ, or [55, 145]. Values beyond ±3σ are rare, occurring less than 0.3% of the time. This rule underpins control charts and outlier detection.

What is the Normal Distribution?

The normal (Gaussian) distribution is the most important continuous probability distribution, modeling natural phenomena that result from many small, independent factors. Its bell shape appears throughout nature, science, and statistics.

Two parameters completely define it: μ (mean) determines location, σ (standard deviation) determines spread. The distribution is symmetric around μ, with probability decreasing exponentially as distance from μ increases.

The normal distribution is fundamental because of the Central Limit Theorem: sums and averages of independent random variables tend toward normality regardless of the original distribution. For comprehensive theory, see normal distribution theory page.

Central Limit Theorem Connection

The Central Limit Theorem explains why normal distributions appear so frequently. When you sum or average many independent random variables, the result approaches a normal distribution even if the original variables aren't normal.

This applies to measurement errors (sum of many small perturbations), test scores (sum of knowledge across many topics), and manufacturing tolerances (sum of variations in multiple processes).

The theorem works surprisingly quickly - often just 30 observations suffice for reasonable normality. This makes the normal distribution applicable even when underlying processes aren't purely Gaussian.

Distribution Properties and Statistics

Mean, median, and mode all equal μ due to perfect symmetry. There's no skewness - the distribution is perfectly balanced around its center.

Variance equals σ², the square of the standard deviation. Standard deviation σ is the natural scale parameter, representing typical deviation from the mean.

The distribution has zero skewness (symmetric) and kurtosis of 3 (defining "normal" tail behavior). Distributions with kurtosis > 3 have heavier tails; kurtosis < 3 have lighter tails than normal.